会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 1. 发明申请
    • NEURAL NETWORK FOR PROCESSING GRAPH DATA
    • 神经网络处理图形数据
    • WO2017040001A1
    • 2017-03-09
    • PCT/US2016/046759
    • 2016-08-12
    • GOOGLE INC.
    • RILEY, Patrick F.BERNDL, Marc
    • G06F19/00G06N3/02G06N99/00
    • G06N3/0454G06F19/707
    • Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving graph data representing an input graph comprising a plurality of vertices connected by edges; generating, from the graph data, vertex input data representing characteristics of each vertex in the input graph and pair input data representing characteristics of pairs of vertices in the input graph; and generating order-invariant features of the input graph using a neural network, wherein the neural network comprises: a first subnetwork configured to generate a first alternative representation of the vertex input data and a first alternative representation of the pair input data from the vertex input data and the pair input data; and a combining layer configured to receive an input alternative representation and to process the input alternative representation to generate the order-invariant features.
    • 方法,系统和装置,包括在计算机存储介质上编码的计算机程序,用于接收表示包括通过边缘连接的多个顶点的输入图形的图形数据; 从图形数据生成表示输入图中每个顶点的特征的顶点输入数据和表示输入图中的顶点对的特征的对输入数据; 以及使用神经网络生成所述输入图的顺序不变特征,其中所述神经网络包括:第一子网络,被配置为生成所述顶点输入数据的第一替代表示和所述顶点输入中的所述对输入数据的第一替代表示 数据和对输入数据; 以及组合层,其被配置为接收输入替代表示并且处理所述输入替代表示以生成所述顺序不变特征。
    • 3. 发明申请
    • TECHNIQUES FOR PROCESSING OF MASS SPECTRAL DATA
    • 用于处理大量光谱数据的技术
    • WO2016196432A1
    • 2016-12-08
    • PCT/US2016/034959
    • 2016-05-31
    • WATERS TECHNOLOGIES CORPORATION
    • GEROMANOS, Scott, J.CIAVARINI, Steven, J.DEVLIN, Curt
    • G06F19/00H01J49/00G01N30/72G01N30/86G01N33/68
    • H01J49/0036G01N30/72G01N30/86G01N30/8675G01N33/68G01N33/6854G06F19/707H01J49/0027H01J49/0031
    • Techniques for performing data acquisition and analysis are described. A multi-mode acquisition strategy may be performed which iteratively selects mass isolation windows of different sizes in different scan cycles to acquire experimental data. The mass isolation windows selected may provide for acquiring elevated energy scan data for a defined set of m/z values. Single scan data analysis may be performed. Data analysis may include forming precursor charge clusters, chaining precursor charge clusters having the same mass to charge ratio to form peaks profiles, and using criteria to align precursor and product ions of the experimental data. Unsupervised and supervised clustering may be performed using a database and composite ion spectra formed from experimental data. Also described are a small molecule acquisition enhancement and additional techniques applicable for biopharmaceutical and other applications.
    • 描述了用于执行数据采集和分析的技术。 可以执行多模式采集策略,其在不同扫描周期中迭代地选择不同大小的质量隔离窗口以获取实验数据。 选择的质量隔离窗口可以提供用于获取用于定义的一组m / z值的升高的能量扫描数据。 可以执行单扫描数据分析。 数据分析可以包括形成前体电荷簇,具有相同质荷比的连接前体电荷簇,以形成峰分布,并使用准则来对准实验数据的前体和产物离子。 可以使用由实验数据形成的数据库和复合离子光谱来执行无监督和监督聚类。 还描述了小分子获取增强和适用于生物制药和其它应用的附加技术。
    • 10. 发明申请
    • SYSTEM AND METHOD FOR MONITORING A PROCESS
    • 用于监测过程的系统和方法
    • WO2014195915A1
    • 2014-12-11
    • PCT/IB2014/062010
    • 2014-06-06
    • SCIENTIFIC DESIGN COMPANY, INC.
    • LAHIRI, Sandip K.HUSAIN, Mansoor
    • G05B23/02G05B17/02
    • G06F19/707G05B23/0216G05B23/024G05B23/0254G05B2219/32201G06F19/702G06N3/02G06N3/08Y02P90/22
    • The present invention concerns a system for monitoring a process determined by a set of process data in a multi-dimensional process data domain pertaining to process input-output data, the system comprising: means for acquiring a plurality of historic process data sets; means for obtaining a transformation from the multidimensional process data domain to a model data domain of lower dimension by performing multivariate data analysis; and means for transforming a current process data set to a model data set to monitor the process. It further concerns a method for monitoring a process determined by a set of process data in a multi¬ dimensional process data domain representing process input-output data, the method comprising: acquiring a plurality of historic process data sets; obtaining a transformation from the multidimensional process data domain to a model data domain of lower dimension by performing multivariate data analysis; and transforming a current process data set to a model data set to monitor the process.
    • 本发明涉及一种用于监视由与过程输入 - 输出数据相关的多维过程数据域中的一组过程数据确定的过程的系统,该系统包括:用于获取多个历史过程数据集的装置; 通过执行多变量数据分析获得从多维过程数据域到较低维度的模型数据域的转换的手段; 以及用于将当前过程数据集转换为模型数据集以监视过程的装置。 还涉及一种用于监视由表示过程输入 - 输出数据的多维过程数据域中的一组过程数据确定的过程的方法,所述方法包括:获取多个历史过程数据集; 通过多变量数据分析获得从多维过程数据域到较低维度的模型数据域的转换; 并将当前处理数据集转换为模型数据集以监视该过程。